Re:Lock-free multithreading with atomic operations
by jchw on Tuesday July 30, 2019 @06:55AM
(#20563647)
Note that lock-free is not always faster because contention is complicated.
[ Parent
| on HN ]
Re:Lock-free multithreading with atomic operations
by vardump on Tuesday July 30, 2019 @07:06AM
(#20563700)
Also note that lock-free can scale worse, again due to contention.
If you want scalability, you want to minimize inter-core and inter-socket traffic.